隐喻自动处理研究进展  

Advancement of the Automatic Metaphor Processing

作　　者：贾玉祥[1] 俞士汶[1] 朱学锋[1] 

机构地区：[1]北京大学计算语言学研究所,北京100871

出　　处：《中文信息学报》2009年第6期46-55,共10页Journal of Chinese Information Processing

基　　金：国家973课题资助项目(2004CB318102);国家自然科学基金资助项目(60773173)

摘　　要：隐喻在人类语言中普遍存在,是自然语言理解必须面对的问题。该文首先探讨了对隐喻的认识及语言中隐喻表达的分类。把隐喻自动处理分为隐喻识别、隐喻理解和隐喻生成三个子任务,对以往的研究成果进行梳理,着重介绍近几年来隐喻自动处理研究的新成果、新特点。隐喻自动处理离不开隐喻知识库的支持,文章也介绍了国内外隐喻知识库建设的主要成果。隐喻自动处理的目的是为了提高自然语言处理的智能化水平,文章探讨了隐喻处理在自然语言处理任务中的应用。最后展望了汉语隐喻自动处理研究的前景。Metaphor is pervasive in human language and must be treated for natural language understanding. Firstly, this paper discusses the nature of metaphor and the manifestation of metaphorical expressions in language. Then the automatic metaphor processing is divided into three subtasks： metaphor recognition, metaphor understanding and metaphor generation. This paper makes an extensive survey of researches on the automatic metaphor processing over the last three decades, emphasizing achievements in recent years. Researches on metaphor knowledge bases are also introduced, which are indispensable for metaphor processing. The applications of metaphor processing to natural language processing tasks are also discussed. Finally, this paper puts forward some suggestions for the future researches on the automatic Chinese metaphor processing.

关 键 词：人工智能 机器翻译 隐喻自动处理 自然语言处理 机器学习 知识获取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]